JP2016509289A - Implied connections in the social graph - Google Patents

Abstract

A method identifies a first user interaction on a social network system and tracing a social graph of the social network system associated with the first user interaction by tracing a social graph of the social network system. Identifying, identifying a user account based on the first user interaction, generating an implicit connection in the social graph between the user account and the social network object, and implicit in the social graph Selecting a content entry for display on a user device signed in by a user account or a friend account based on the connection, the friend account It has led to the social to the user account through the social graph of the network system.

Description

  The present invention relates generally to social networking, and more particularly to inferring connections in a social graph from a social networking system.

  Social networking systems generally provide a mechanism for users to interact within their social network. A social networking system user is an individual or any other entity, such as a business or other entity other than a human. Various connections, including connections between users and social objects in a social networking system, including connections from one user to another, connections from a user to a social object, and connections from a social object to another social object Relationships are tracked within the social networking system. Social objects include, for example, social networking system users, non-human entities, content items, groups, social networking system pages, events, messages, subjects (such as people, places, things, abstract ideas or concepts), multimedia, Or one or more of any combination thereof.

  Social networking system information tracked and maintained by the social networking system is stored as a social graph, which includes a plurality of nodes interconnected by a plurality of edges. A social graph node represents a social networking system object that acts on and / or is acted upon by another node. Each of these interactions is stored as a social graph edge. In one embodiment, the edges are represented as bidirectional. In other embodiments, the edges are represented as unidirectional. For example, a user node checking in to a social network page for location is represented by either a bidirectional edge between the user node and the social network page or a unidirectional edge from the user node to the social network page. Is done. The social graph is therefore stored as a database of edges between nodes. In one embodiment, the social graph is stored separately for a particular type of user interaction. In other embodiments, the social networking system stores the social graph without distinguishing the type of user interaction.

  An edge between nodes in a social graph represents a specific type of connection between those nodes, and that specific type of connection is performed by one of those nodes on the other node Results from the action taken. Examples of such actions by a social networking system user include listing social networking system objects in a user profile, subscribing to or participating in a social networking system group or fan page, and messages to another social networking system user Sending to, making a purchase associated with a social networking system node, commenting on a content item, or booking an event (asking for a reply to an invitation to an event).

One category of edges in social networks is page connections. A page connection is a connection between a user account and a social networking system page. The social networking system page is a portal for entities to interact with social networking system users. A social networking system page represents an entity, brand, individual, company, group, organization, or any combination thereof. Page connections are used in advertising, news feeds, data collection, and various other tasks.

  Page connections created using conventional systems often represent explicit approvals for connections from social networking system users to social networking system pages. For example, a page connection is created when a social networking system user clicks a “like” button on a social networking system page. This type of connection creation may limit the richness in connection information with social networking systems.

  Embodiments of the present invention generate and utilize implicit connections in social graphs in social networking system communications. In one embodiment, the implicit connection in the social graph is identified from the social graph of the social networking system. Implicit connections in the social graph are exploited from one or more recorded user interactions. User interaction is received from a client device connected to the social networking system through a user account.

  In the figures and detailed description, by way of example, it is shown that an implicit connection in a social graph exists between a user account and a social network page, but the techniques disclosed herein are optional It can be seen that this applies to the implicit connection in the social graph from any social graph object to any other social graph object.

  For example, from the user interaction, the connection generation module identifies a user account associated with the user interaction and a social network object such as a social network page. An implicit connection in the social graph is added to the social graph based on the identified user account and social network object. Implicit connections in the social graph are generated in parallel batch processing in response to identifying user interactions or by examining the social graph. The connection generation module can also calculate edge weights for implicit connections in the social graph, in which case the edge weights are then chosen by the user to create an explicit connection with the social network object. Quantitative probability to be identified. Many examples of how implicit connections in social graphs are identified by user interaction are described below.

  Further, in one embodiment, the social networking system includes a connection usage module. The connection utilization module uses an implicit connection in the social graph to select a particular content item for presentation to the client. The connection usage module selects ad objects, news feed stories, widgets, personalization content, or any combination thereof based on the implicit connection in the social graph and the edge weights of the implicit connection in the social graph To do.

Social networking systems improve the accuracy of content personalization based on the disclosed mechanisms. For example, advertisements shown in a user account, or a friend account of a user account, are better personalized based on interactions associated with a particular social network object. A friend account is another user account associated with a user account, and the association is established by explicit confirmation of each other. Accordingly, embodiments of the present invention have been found to improve social networking system personalization technology and improve the breadth of businesses with social network objects.

  One embodiment has other aspects, elements, functions, and steps in addition to or in place of those described above. These potential additions and alternatives are described throughout the remainder of this specification.

1 illustrates a social networking system with a mechanism for generating an implicit connection in a social graph. FIG. 1 is a high-level block diagram of a system environment suitable for a social networking system, according to one embodiment. The control flow of the social networking system that operates the connection system. An example social graph illustrating the derivation of an implicit connection in a social graph through a direct interaction process. An example social graph illustrating the derivation of an implicit connection in a social graph through a direct interaction process. An example social graph showing the derivation of an implicit connection in the social graph by an active reaching process. An example social graph showing the derivation of an implicit connection in the social graph by an active reaching process. An example social graph showing the derivation of an implicit connection in the social graph by an active reaching process. An example social graph showing the derivation of an implicit connection in a social graph by a passive connection process. An example social graph showing the derivation of an implicit connection in a social graph by a passive connection process. An example social graph showing the derivation of an implicit connection in a social graph by a passive connection process. An example social graph showing the derivation of an implicit connection in a social graph through a bridge interaction process. An example social graph showing the derivation of an implicit connection in a social graph through a bridge interaction process. An example social graph showing the derivation of an implicit connection in a social graph through a bridge interaction process. An example social graph showing the derivation of an implicit connection in the social graph through the account attribute process. An example social graph showing the derivation of an implicit connection in the social graph through the account attribute process. 2 is a flowchart of a method for operating a social networking system. FIG. 7 is a diagram representing a machine in an exemplary form of a computer system on which a set of instructions for causing a machine to execute any one or more of the methods or modules described herein are executed.

  These figures depict various embodiments for purposes of illustration only. Those skilled in the art will readily recognize from the following discussion that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles described herein. Will.

Social Networking System Overview Social networking systems generally provide a mechanism for users to interact with objects and other users both inside and outside the context of the social networking system. A social networking system user is an individual or any other entity, such as a business or other entity other than a human. Social networking systems utilize a web-based interface that includes a series of interconnected pages. This interface allows social networking system objects and information to be displayed and the user to interact with them. For example, the social networking system displays a page for each user of the social networking system that includes objects and information entered by or related to the social networking system user (eg, the user's “profile” ")including. A social networking system includes a page, which includes an image or video, is dedicated to a concept, is dedicated to users of similar interest ("groups"), or to other users, from other users Or other user communications or social networking system activities. The social networking system page can include links to other social networking system pages, and additional features such as search, real-time communication, content item uploads, purchases, advertisements, and any other web-based technology or capability including. Note that the social networking system interface can be accessed from a web browser or an application other than a web browser, eg, a mobile device dedicated to the social networking system or a computer application. Thus, a “page” as used herein is a web page, application interface or display, a widget displayed on a web page or application, a box or other graphical interface, an overlay window on another page (Whether within or outside the context of the social networking system) or an external web page of the social networking system with social networking system plug-ins or integration capabilities.

As described above, a social graph includes a set of nodes (representing social networking system objects, also known as social objects) that are interconnected by edges (representing interactions, activities, or relationships). Social networking system objects can be social networking system users, non-human entities, content items, groups, social networking system pages, locations, applications, subjects, concepts, or other social networking system objects, such as movies, bands, or books It is. Content items can be anything that a social networking system user or other object creates, uploads, edits, or interacts with, eg, messages, queued messages (eg, emails), text and SMS ( Short message service) messages, comment messages, messages sent using any other suitable messaging technology, HTTP links, HTML files, images, video, audio clips, documents, document editing, calendar entries or events, and Contains other computer related files. Themes and concepts include nodes that represent any person, place, thing, or abstract idea in the context of a social graph.

  Social networking systems allow users to enter and display information related to their interests, education and work experience, contact information, and other background information in their profile pages. Included within each school, employer, interest (eg, music, books, movies, TV shows, games, political views, philosophy, religion, group, or fan page), geographic location, network, or profile page Any other information that is represented is represented by a node in the social graph. A social networking system allows a user to upload or create images, videos, documents, songs, or other content items, and allows the user to create and schedule events. Content items and events are represented by nodes in the social graph.

  Social networking systems provide various means for interacting with non-human objects within the social networking system. For example, users can form a group within a social networking system, join a group, or become a fan of a fan page. In addition, users can create, download, browse, upload, link to, tag social networking system objects, edit social networking system objects, Or you can play. A user can interact with social networking system objects outside the context of the social networking system. For example, an article on a news website may have a “like” button that the user clicks. In each of these cases, the interaction between the user and the object is represented by an edge in the social graph that connects the user node to the object node. A user can “check in” to a specific location using a location sensing function (such as a GPS receiver on a mobile device) and the edge connects the user node to the location node in the social graph Can do.

  Social networking systems allow users to associate themselves and establish connections with other users of the social networking system. If two users explicitly establish a connection in the social networking system, they become “friends” (or “connections”) in the context of the social networking system. Being friends in a social networking system allows users to access more information about each other than is otherwise available to users who are not connected. For example, being a friend allows the user to view another user's profile, see another user's friend, or view another user's image. Similarly, making friends within a social networking system communicates with another user, such as by email (inside and outside the social networking system), instant messaging, text messaging, phone calls, or any other communication interface To allow users more access to Being a friend allows a user access to view, comment, download, recommend, or otherwise interact with content items uploaded by another user. Establishing connections, accessing user information, communicating, and interacting within the context of a social networking system is represented by an edge between the nodes representing the two social networking system users.

  In addition to explicitly establishing connections within a social networking system, users with common characteristics are connected for the purpose of identifying social contexts for use in identifying communication topics ( Soft or implied connection). In one embodiment, users belonging to a common network are considered connected. For example, users who go to a common school, work at a common company, or belong to a common social networking system group are considered connected. In one embodiment, users with common background features are considered connected. For example, the geographic region in which the user was born or lived, the user's age, the user's gender, and the user's dating status are used to identify whether the users are connected. In one embodiment, users with a common interest are considered connected. For example, a user's movie preferences, music preferences, political views, religious views, or any other interest is used to identify whether the users are connected. In one embodiment, users who have taken a common action within a social networking system are considered connected. For example, users who are recommending or recommending common objects, commenting on common content items, or seeking answers to invitations to common events are considered connected. Social networking systems utilize social graphs to identify users connected with a particular user for the purpose of identifying or evaluating the social context of a particular user's communication, as described in more detail below. .

  Social networking systems provide users with various communication channels. For example, a social networking system allows a user to send an e-mail, send an instant message, or send a text / SMS message to one or more other users, who can send their own wall or profile Alternatively, you can post a message on another user's wall or profile, the user can post a message on a group or fan page, or the user can create an image or wall created or uploaded by himself or another user You can comment on posts or other content items. In one embodiment, the user can post a status message to the user's profile indicating current events, feelings, thoughts, emotions, activities, or any other current relevant communication. A social networking system allows a user to communicate both inside and outside the social networking system. For example, a first user may send a message within a social networking system, an email through the social networking system, an email that is external to the social networking system but originating from the social networking system, an instant message within the social networking system, And an instant message originating outside the social networking system but originating from the social networking system can be sent to the second user. Further, the first user can comment on the second user's profile page or can comment on an object associated with the second user, such as a content item uploaded by the second user. it can.

  An explicit connection in the social graph (“explicit connection”) is intended to let the social networking system know that there is an association between the initiator and the target when the initiator is interested in more information about the target Defined as an intentional user interaction recorded in Initiators and targets are social graph nodes. For example, a friend request from “John Doe” to “Jane Smith” is an explicit link.

  Explicit page connections are recorded for the purpose of instructing the social networking system that an association exists between the user account and the target page and that the user of the user account is interested in more information about the target page Defined as intentional user interaction. For explicit page connections, the initiator is a user account. The target in the explicit page connection case is the social networking system page. For example, it is an explicit page connection that a user “John Doe” asserts “Like” for a page related to his favorite band “Morning Band”. For example, it can be said that a user account commenting on a target page is a direct and intentional interaction. This interaction does not establish an explicit page connection. This is because the user account does not indicate in explicit terms that the user account is interested in more information about the target page.

  An implied connection in a social graph (“implicit connection”) is not an explicit connection, any user established between the user account and the target page for the user account and the target page by the social networking system Defined as a connection. Similarly, an implicit page connection is defined as any connection established by the social networking system between the user account and the target page for the user account and the target page that is not an explicit page connection. This disclosure describes methods and system mechanisms for generating and identifying implicit connections in these social graphs that include implicit page connections.

  Referring now to FIG. 1, a social networking system 100 with a mechanism for generating an implicit connection in a social graph is shown. Social networking system 100 is a social networking system as described in the overview. The social networking system 100 includes a connection system 102 that functions within the social networking system 100 to generate an implicit connection 104 in a social graph, such as an implicit page connection.

  Social networking system 100 provides user interaction 106 to connection system 102. User interaction 106 is received from the client device and recorded on social networking system 100.

  Social networking system 100 includes a social graph 108. The social graph 108 is a social graph as described in the overview, including connections between various node entities such as user accounts, social network pages, interest groups, and other entities.

  The connection system 102 takes the user interaction 106 and follows the social graph 108 to identify if there is a connection that can be a new implicit connection in the social graph. Connection system 102 identifies a user account associated with user interaction 106, such as user account 110. The user account 110 is a user account that has started the user interaction 106. User account 110 may be directly involved in user interaction 106. For example, if the user interaction 106 is a message post, the user account 110 is the owner of the message wall where the message post is placed. User account 110 may be indirectly involved in user interaction 106, in which case user account 110 is directly associated with another entity that is directly involved in user interaction 106.

  The connection system 102 identifies a social network object 112 associated with the user interaction 106, such as a social network page. Social network object 112 is a social network page involved in user interaction 106. Social network object 112 is also identified when a reference, link, or content of social network object 112 is associated with user interaction 106. For example, if a promotion, coupon, message, multimedia sharing post, or gift from social network object 112 is involved in user interaction 106, social network object 112 is identified by connection system 102. Social network object 112 is identified when a reference, link, or content of social network object 112 is indirectly related to user interaction 106. For example, if user interaction 106 involves user account 110 tagging a friend account in a photo, and that friend account already references a link to social network object 112 on that photo. The social network object 112 is identified by the connection system 102 as being indirectly related to the user interaction 106.

  Once the connection system 102 identifies the user account 110 and the social network object 112, the connection system 102 generates an implicit connection 104 in the social graph. An implicit connection 104 in the social graph is an implicit connection in the social graph as defined above between a social network page and a user account, such as the social network object 112 and user account 110 in the social graph 108. is there. The implicit connection 104 in the social graph is stored in a stand-alone database or stored back to the social graph 108 of the social networking system 100.

  The connection system 102 calculates the edge weight (W) 114 associated with the implicit connection 104 in the social graph. The edge weight 114 is an indication of how likely the user of the user account 110 will see an explicit connection in the social graph with the social network object 112. The edge weights 114 are based on the type of user interaction 106. The edge weight 114 may indicate whether the user account 110 has initiated the user interaction 106, whether the user account 110 is directly involved in the user interaction 106, or whether the user account 110 is indirectly associated with the user interaction 106. It may be based on whether or not it is involved. The edge weight 114 is based on whether the social network object 112 is directly or indirectly related to the user interaction 106. The edge weight 114 may be adjusted based on further subsequent instances of the user interaction 106. In one embodiment, the first interaction associated with the user account 110 and the social network object 112 can generate an instance of the implicit connection 104 in the social graph, and then the same user account 110 and the same social Subsequent interactions of the same type associated with the network object 112 adjust the edge weights 114 of the implicit connection 104 in the social graph. In other words, the frequency of instances of the user interaction 106 affects the edge weight 114.

Referring now to FIG. 2, a high level block diagram of a system environment 200 suitable for social networking system 202 is shown, according to one embodiment.
The system environment 200 shown in FIG. 2 includes a social networking system 202, a client device 204A, and a network channel 206. The system environment 200 includes a client device 204B and a client device 20
Also includes other client devices, such as 4C. In other embodiments, the system environment 200 includes different and / or additional components than those illustrated by FIG. The social networking system 202 is the social networking system 100 of FIG.

Social Networking System Environment and Architecture The social networking system 202 is associated with users and / or other objects and connections between users and other users and / or objects, as further described below. One or more computing devices for storing user profiles are provided. In use, a user joins the social networking system 202 and then adds a connection to other users or objects in the social networking system that they want to connect to. As described further below in connection with FIG. 2, a user of social networking system 202 is an individual or entity, such as a company, organization, university, manufacturer. Social networking system 202 allows the users to interact with each other and other objects maintained by social networking system 202. In one embodiment, the social networking system 202 allows users to interact with third party websites and financial account providers.

  Based on stored data regarding users, objects, and connections between users and / or objects, social networking system 202 creates a “social graph” that includes multiple nodes interconnected by multiple edges. Generate and maintain. This social graph is the social graph 108 of FIG. Each node in the social graph represents an object or user that can act on and / or be acted on by another node. An edge between two nodes in a social graph indicates a particular type of connection between two nodes that can result from actions performed by one of those nodes on the other node Represent. For example, if the user identifies a further user as a friend, an edge in the social graph is generated connecting the node representing the first user and the further node representing the further user. The generated edges have a connection type that indicates that those users are friends. As the various nodes interact with each other, the social networking system 202 adds and / or modifies the edges that connect the various nodes to reflect those interactions.

Client device 204A is a computing device capable of receiving user input and transmitting and / or receiving data over network channel 206. In one embodiment, client device 204A is a conventional computer system, such as a desktop or laptop computer. In another embodiment, client device 204A is a device having computer functionality, such as a personal digital assistant (PDA), mobile phone, tablet, smartphone, or similar device. In yet another embodiment, client device 204A is a virtualized desktop that runs on a cloud computing service. Client device 204A is configured to communicate with social networking system 202 and / or financial account provider through network channel 206. In one embodiment, client device 204A runs an application that allows a user of client device 204A to interact with social networking system 202. For example, client device 204A executes a browser application to allow interaction between client device 204A and social networking system 202 through network channel 206. In another embodiment, the client device 204A interacts with the social networking system 202 through an application programming interface (API) that runs on the native operating system of the client device 204A, such as IOS® or ANDROID®.

  Client device 204A is configured to communicate over network channel 206, which can be any combination of local and / or wide area networks that use both wired and wireless communication systems. including. In one embodiment, the network channel 206 uses standard communication technologies and / or standard protocols. Therefore, the network channel 206 uses technologies such as Ethernet (registered trademark), 802.11, World Wide Interoperability for Microwave Access (WiMAX), 3G, 4G, CDMA, Digital Subscriber Line (DSL), etc. Contains links to Similarly, the networking protocols used on the network channel 206 are Multiprotocol Label Switching (MPLS), Transmission Control Protocol / Internet Protocol (TCP / IP), User Datagram Protocol (UDP), Hypertext Transport Protocol (HTTP) ), Simple Mail Transfer Protocol (SMTP), and File Transfer Protocol (FTP). Data exchanged through the network channel 206 is represented using technologies and / or formats including hypertext markup language (HTML) or extensible markup language (XML). In addition, all or some of the links are encrypted using conventional encryption techniques such as Secure Sockets Layer (SSL), Transport Layer Security (TLS), and Internet Protocol Security (IPsec). .

  The social networking system 202 illustrated by FIG. 2 includes a profile store 210, content store 212, action logger 214, action log 216, edge store 218, financial account store 220, connection system 222, web server 224, message server 226, And an API request server 228. In other embodiments, the social networking system 202 includes additional, fewer, or other modules for various applications. Conventional components such as network interfaces, security mechanisms, load balancers, failover servers, management and network operations consoles are not shown so as not to obscure the details of this system architecture.

Each user of social networking system 202 is associated with a user profile, which is stored in profile store 210. The user profile includes declarative information about the user explicitly shared by the user and includes profile information inferred by the social networking system 202. In one embodiment, the user profile includes a plurality of data fields, each data field describing one or more attributes of a corresponding user of the social networking system 202. User profile information stored in the profile store 210 includes background information, demographic information, and other types of descriptive information, such as work experience, educational background, gender, hobbies or preferences, location, etc. Describes the user of the social networking system 104. The user profile stores other information provided by the user, such as an image or video. In certain embodiments, the user's image is tagged with the identity of the user of the social networking system 202 displayed in the image. The user profile in the profile store 210 maintains a reference to the action by the corresponding user that is executed on the content item in the content store 212 and stored in the edge store 218.

  As described further below, the user profile is associated with one or more financial accounts, thereby allowing the user profile to include data retrieved or derived from the financial account. The user can specify one or more privacy settings, which are stored in the user profile and limit information from financial accounts that the social networking system 202 is allowed to access. . For example, privacy settings limit social networking system 202 to access financial account transaction history and not current account balances. As another example, the privacy settings limit the social networking system 202 to a subset of the financial account's transaction history so that the social networking system 202 is more than a transaction within a specified time range, a threshold transaction amount. Identified by a user that is also accessible by the social networking system 202, a transaction involving a small amount, a transaction associated with a specified vendor identifier, a transaction associated with a vendor identifier other than a specified vendor identifier, or It will be possible to access transactions on any suitable basis that limits information from financial accounts. In one embodiment, information from the financial account is stored in the profile store 210. In other embodiments, information from the financial account is stored in the financial account store 220.

  Content store 212 stores content items associated with a user profile, such as images, videos, or audio files. Content items from the content store 212 are displayed when a user profile is viewed or when other content associated with the user profile is viewed. For example, the displayed content item shows an image or video associated with the user profile or shows text describing the user's condition. In addition, other content items are new to expand the user's connection to other users by displaying content related to the user, object, activity, or functionality of the social networking system 202. Facilitate user engagement by encouraging new users to interact with the system or to increase interaction with social network systems. Examples of social networking content items include proposed connections or suggestions to perform other actions, media provided to or maintained by the social networking system 202 (eg, images or videos). ), Status messages or links posted by users to social networking systems, events, groups, pages (for example, representing an organization or commercial entity) provided by or accessible through social networking systems, and others Any content is included.

Content store 212 also includes one or more pages associated with entities having a user profile in profile store 210. An entity is a non-individual user of social networking system 202, such as a company, vendor, organization, or university. The page includes content associated with the entity and instructions for presenting the content to a social networking system user. For example, the page identifies content that is associated with the user profile of the entity as well as information that describes how to present that content to users viewing the brand page. Vendors are associated with pages in content store 212, which allows social networking system users to more easily interact with vendors through social networking system 202. The vendor identifier is associated with the vendor's page so that social networking system 202 can use the vendor identifier to identify the vendor and / or from profile store 210, action log 216, or other It will be possible to retrieve further information about the vendor from any suitable source. In one embodiment, the content store 212 stores one or more targeting criteria that identify one or more characteristics of a user associated with the stored object and eligible to be presented with the object. To do.

  Action logger 214 receives communications regarding user actions on and / or outside of social networking system 202 and populates action log 216 with information regarding user actions. Such actions include, among other things, adding a connection to another user, sending a message to another user, uploading an image, reading a message from another user, Browsing content associated with another user, attending an event posted by another user. In one embodiment, action logger 214 receives transaction information from a financial account associated with the user and identifies user actions from the transaction information according to one or more privacy settings. For example, the action logger 214 retrieves a vendor identifier from the financial account transaction history and identifies an object, such as a page in the social networking system, associated with the vendor identifier. This allows the action logger 214 to identify purchases by users of products or services associated with a page or another object in the content store 212. In addition, the actions described in relation to other objects are targeted to specific users, so these actions are also associated with those users. These actions are stored in the action log 216.

  According to various embodiments, action logger 214 receives communications from web server 224 regarding user actions on and / or outside of social networking system 200. The action logger 214 inputs information about user actions into the action log 216 to track those user actions. This information follows the privacy settings associated with the user. Any action a particular user takes on another user is associated with each user's profile through information maintained in a database or other data repository, eg, action log 216. Such actions include, for example, adding connections to other users, sending messages to other users, reading messages from other users, and content associated with other users. Including viewing, attending an event posted by another user, being tagged in a photo with another user, saying "like" to an entity, etc.

The action log 216 is used by the social networking system 202 to track user actions on the social networking system 202 as well as external websites that communicate information to the social networking system 202. A social networking system that includes users commenting on posts, sharing links and checking in physical locations through mobile devices, accessing content items in a sequence, or other interactions Interact with various objects on 202. Information describing these actions is stored in the action log 216. Further examples of interactions with objects on the social networking system 202 included in the action log 216 include commenting on photo albums, communication between users, becoming a musician fan, and adding events to the calendar. , Joining a group, becoming a fan of a brand page, creating an event, approving an application, using an application, and engaging in a transaction. In addition, the action log 216 records advertisements on the social networking system 202 and user interactions with applications running on the social networking system 202. In one embodiment, the data from the action log 216 is used to infer user interest or preferences to augment the interest associated with the user profile and allow a more complete understanding of the user preferences. To do.

  In addition, user actions that occur in a particular context, such as when the user is presented with specific content on the social networking system 200, or appears to be accessing that content, are accompanied by that specific context. Captured and logged. For example, a particular user is shown / not shown information about the user candidate each time that particular user accesses the social networking system 200 for a fixed period of time. Any action taken by the user during this time period is logged with context information (ie, the user candidate was / was not provided to a particular user) and recorded in the action log 216. The In addition, the actions described below in relation to other objects are directed to specific users, and therefore these actions are also associated with those users.

  The action log 216 stores user actions taken on external websites and / or identified from financial accounts associated with the user. For example, an e-commerce website that primarily sells sporting goods at bargain prices recognizes the user of the social networking system 202 through a social plug-in that identifies the user of the social networking system 202. Since users of the social networking system 202 are uniquely identifiable, e-commerce websites such as this sporting goods retailer use information about these users when they visit their website. The action log 216 records data about these users, including web page browsing history, advertisements involved, purchases made, and other patterns from shopping and shopping. For actions identified by the action logger 214 from the transaction history of the financial account associated with the user, the action log 216 records further information regarding additional types of user actions.

In one embodiment, the edge store 218 stores information in the edge object that describes the connection between the user and other objects on the social networking system 202. The edge store 218 stores the social graph described above, such as the social graph 108 of FIG. Some edges are defined by the user, which allows the user to specify their relationship with other users. For example, a user generates an edge with other users who are similar to their real life relationships, such as friends, colleagues, partners, and the like. Other edges comment on users' interest in pages on social networking systems, sharing links with other users of social networking systems, and posts made by other users of social networking systems And so on when interacting with objects in the social networking system 202. The edge store 218 stores edge objects that contain information about edges, such as objects, interests, and other user familiarity scores. The familiarity score is calculated by the social networking system 202 over time to estimate the user's familiarity with objects, interests, and other users within the social networking system 202 based on actions performed by the user. In one embodiment, multiple interactions of the same type between the user and a particular object are stored in one edge object in edge store 218. In one embodiment, connections between users are stored in profile store 210 or profile store 210 accesses edge store 218 to identify connections between users. The user makes a selection from a predefined type of connection, or defines his own connection type as needed.

  Web server 224 links social networking system 200 to one or more client devices over a network, and web server 224 provides web pages, as well as other web-related content, such as Java, Flash, XML, etc. Supply. The web server 224 communicates with a message server 226 that provides functionality for receiving and forwarding messages between the social networking system 200 and client devices. Messages processed by message server 226 are instant messages, queued messages (eg, email), text and SMS (Short Message Service) messages, or any other suitable messaging technology. In one embodiment, a message sent by a user to another user is viewed by other users of social networking system 200, for example, by the user's connection to receive the message. One example of a type of message viewed by other users of the social networking system other than the message recipient is a wall post. In one embodiment, a user sends a private message to another user that can only be retrieved by that other user.

  The API request server 228 accesses information from the social networking system 200 by an external system calling the API. The information provided by the social network includes user profile information or connection information of the user specified by the user's personal privacy settings. For example, a system that is interested in predicting the likelihood that a user will form a connection within the social networking system sends an API request to the social networking system 200 over the network. The API request is received at the social networking system 200 by the API request server 228. The API request server 228 processes the request by identifying the appropriate response, and the request is then sent back over the network to the requesting system.

  Social networking system 202 also includes a connection system 222. The connection system 222 is the connection system 102 of FIG. The connection system 222 accesses the stores and modules of the social networking system 202 to identify implicit connections in the new social graph. The connection system 222 receives user interaction from the client device 204A to identify connections that can be new implicit connections in the social graph. Once the implicit connection in the social graph is generated and stored, the connection system 222 may use the social networking system to utilize the implicit connection in the social graph for the purpose of selecting content for display on the client device 204A. Cooperate with 202 other modules and stores.

Referring now to FIG. 3, the control flow of the social networking system 300 that operates the connection system 301 is shown. The connection system 301 is the connection system 102 of FIG. 1 or the connection system 222 of FIG. The connection system 301 is for identifying an implicit connection in a social graph from at least one social graph, such as the social graph 108 of FIG. The implicit connection in the social graph is then stored back in the social graph, for example, in the edge store 302 or connection store 304. For example, the connection system 301 identifies an implicit connection in the social graph from the social graph represented by the edge store 302. The edge store 302 is the edge store 218 of FIG. The connection system 301 includes user interaction from the action log 306, user profile from the profile store 308, and content store 310, such as the action log 216 in FIG. 2, the profile store 210 in FIG. 2, and the content store 212 in FIG. 2. Access social network content.

  The connection system 301 is implemented by a computer system with at least one processor and one non-transitory memory. The connection system 301 exists on the same computer system as the social networking system 100 of FIG. 1 or the social networking system 202 of FIG. The connection system 301 is implemented by the computer system of FIG.

  The connection system 301 includes one or more methods for identifying an implicit connection in a social graph from a user interaction and / or social graph of a social networking system 300 such as the social networking system 100 of FIG. Those one or more methods are implemented by the components, storage, and modules described below. Those modules are implemented as hardware components, software modules, or any combination thereof. For example, the modules described are software modules implemented as instructions in non-transitory memory that are executed by a processor or controller on the machine described in FIG.

  Each of these modules functions independently from the other modules. Some or all of these modules are combined as one module. A single module is divided into a plurality of sub-modules, each performing one or more individual method steps of the single module. Modules share access to one memory area. One module accesses data that is accessed or converted by another module. If modules share a physical or virtual connection directly or indirectly so that data accessed or modified from one module is accessed in another module The modules are considered “coupled” to each other.

  The storage or “store” described below is a hardware component or part of a hardware component for storing digital data. Each of the storages can be a single physical entity or can be distributed across multiple physical devices. Each of the storages can reside on a separate physical device or share the same physical device or devices. Each store can be allocated a specific storage area for a runtime application.

  The connection system 301 includes additional, fewer, or other modules for various applications. Conventional components such as network interfaces, security functions, load balancers, failover servers, management and network operations consoles are not shown so as not to obscure the details of this system.

The connection system 301 includes two main modules, a connection generation module 314 and a connection use module 316. The connection generation module 314 is for generating an implicit connection in the social graph. The connection usage module 316 is for selecting one or more content entries to present to the user account based on the implicit connection in the social graph.

  The connection generation module 314 includes an explicit connection generation module 318. The explicit connection generation module 318 is for generating and storing an explicit connection in the social graph. The explicit connection generation module 318 accesses user interactions that show explicit connections in the social graph. For example, explicit connection generation module 318 identifies “like” or “subscribe” actions from action log 306. A “like” or “subscribe” action directly indicates that a user account, such as user account 110 of FIG. 1, is interested in receiving further information from a social network page, such as social network object 112 of FIG. And explicitly indicated. The explicit connection generation module 318 generates an explicit connection in the social graph between the user account and the social network page. The explicit connection generation module 318 then stores the connections in the generated social graph in the edge store 302 or connection store 304.

  The connection generation module 314 includes an implicit connection generation module 320. The implicit connection generation module 320 is for generating and storing an implicit connection in the social graph. The implicit connection generation module 320 accesses user interaction from the action log 306 that shows implicit connections in the social graph. The implicit connection generation module 320 generates an implicit connection in the social graph by identifying a user account from the user interaction and identifying a social network page from the user interaction. Identifying the user account includes identifying the user account that initiated the user interaction. Identifying the user account includes identifying the user account involved in the user interaction, directly or indirectly, as described in FIG. Identifying a user account means that when a user account involves another user account in a user interaction, it shares one or more attributes that are the same as that other user account. Including identifying. For example, the user account exists at the same time and in the same location as other user accounts that have created an explicit connection in the social graph with the social network page. As another example, a user account is part of an event when most other user accounts in an event have checked in to a social network page.

  Identifying the social network page includes identifying the social network page by identifying a link, reference, or content of the social network page involved in the user interaction. This inclusion is included directly or indirectly as described in FIG.

  The implicit connection generation module 320 is based on a long list of user interaction types. This long list of user interaction types is used to compare with incoming user interactions in order to identify whether an implicit connection in the social graph should be generated.

The connection generation module 314 includes a weight calculation module 322. The weight calculation module 322 is for specifying the edge weight of the connection in the social graph generated by the implicit connection generation module 320 or the explicit connection generation module 318. For example, a connection in a social graph exists between a user account and a social network page. The edge weight is the edge weight 114 of FIG. The edge weight represents a quantitative probability estimate that the user will subsequently choose to create an explicit connection with the social network page. An explicit connection always has the highest probability represented by the edge weight. The weight calculation module 322 identifies edge weights based on a plurality of factors and adjusts the edge weights to be proportional to the strength of the implicit connection in the social graph.

  For example, the weight calculation module 322 identifies edge weights based on a first location record of the user account and a second location record of the social network page. The weight calculation module 322 further weights the implicit connection in the generated social graph when the residence or current location of the user account is close to the physical location of the entity behind the social network page.

  In another example, the weight calculation module 322 is an iterative process. The weight calculation module 322 first identifies the weights of the implicitly connected edges in the newly generated social graph. As new user interactions are received by the weight calculation module 322, the weight calculation module 322 adjusts the edge weights based on those new user interactions. For example, user interaction by a user (eg, a check-in action associated with a page in a social network) generates an implicit connection in a social graph with edge weights. Subsequent interaction by the user (eg, another check-in action associated with the same page) increases the edge weight between the user account and the social network page. The edge weight is then based on the history of user interactions associated with the user account and social network pages. This makes it possible to capture the frequency of user interactions with social network pages directly or indirectly. This adjustment of edge weights occurs for the same type of interaction. In one embodiment, this adjustment of edge weights occurs for different types of interactions associated with the same user account and the same social network object. It has been found that the frequency of user interaction is proportional to the probability that the user will subsequently establish an explicit connection. Thus, the edge weights are adjusted based on further interactions, eg, increasing the edge weights in proportion to each further interaction.

  In yet another example, the weight calculation module 322 identifies edge weights based on the account profile of the user account. The account profile is retrieved from the profile store 308. In yet another example, the weight calculation module 322 identifies edge weights based on the page profile of the social network page. The page profile is retrieved from the profile store 308. The page profile includes the entity's business type. For example, the page profile of a social network page includes that the social network page is a museum or a restaurant. If the entity type is a museum, the edge weights are greater given the same frequency of user interaction between the user account and the social network page as compared to a restaurant. This allows the system to recognize a strong association with the business type of the entity that does not frequently expose the entity itself to user interaction.

In a further example, the weight calculation module 322 identifies edge weights based on an edge weight model. The edge weight model is a function of user interaction that plays a role in generating an implicit connection in the social graph. The edge weight model is a function of the frequency of user interaction between an implicitly connected user account in the social graph and an implicitly connected social network page in the social graph. In a specific example, the edge weight model is an edge weight of 1 if the user account is tagged or checked in on a social network page once a month. The edge weight model has an edge weight of 5 if the user account has checked in to the social network page twice a month. If the user account checks in three times a month, the edge weight is 20. The edge weight model is a non-linear function of the frequency of user interaction.

  Edge weight models are generated or trained based on explicit connections in the social graph within the social graph. The edge weight model is specific to the page type and user account type in the social graph. If a particular type of user interaction in the social graph creates a more explicit connection, the edge weight model recognizes that particular type of user interaction and social graph layout as corresponding to a large edge weight value To do.

  In one embodiment, the edge weight model is based on various other types of user interaction. A specific edge weight function is assigned to each of the user interaction types. The weight function of that particular edge is based on user profile attributes, page profile attributes, user interaction frequency, or any combination thereof.

  When a connection in the social graph is generated by the implicit connection generation module 320 or the explicit connection generation module 318, the connection in the social graph is stored back in the edge store 302 or connection store 304. The weight of each edge of the connections in the social graph is also stored in the edge store 302 or connection store 304.

  The connection generation module 314 includes a node expansion module 324. The node expansion module 324 removes the association chain in the social graph between the user account node and the social network page node, making it a direct link between the user account and the social network page, It is for generating an implicit connection in a new social graph. For example, if a user account is associated with a friend account, and the friend account is explicitly subscribed to a social network page, the node deployment module 324 may identify the user account and social network page. Create an implicit connection in the social graph between.

The connection generation module 314 includes a social plug-in module 326. The social plug-in module 326 is for receiving user interaction from the social plug-in instead of the action log 306. Social plug-ins are tools used by other websites to provide people with a personalized social experience. When an external user account at another website interacts with a social plug-in, the external user account shares an external user experience outside of the social networking system 300 with a user account on the social networking system 300. The social plug-in includes a user interface for interacting with content in the social networking system 300. For example, the social plug-in module 326 receives and provides the user interaction 106 of FIG. 1 for the connection generation module 314. In a specific example, an external user account is logged into Spotify ™, and the external user account is “David.
I listen to many songs from Bowie. In that specific example, the social plug-in module 326 provides a user interaction to listen to songs from a social network page about “David Bowie” to the connection generation module 314.

  The connection utilization module 316 includes a feed selection module 328. The feed selection module 328 is for presenting a news feed story to a user of the social networking system 300 based on a social graph. A newsfeed is composed of one or more news stories, each story containing one or more items of media content. The feed selection module 328 selects one or more generated stories for the news feed based at least in part on the weight of the implicit connection edge in the social graph.

  In one embodiment, the feed selection module 328 uses an implicit connection in the social graph to select a news feed story. In other embodiments, the implicit connection in the social graph is also used to select other media content for presentation to the user. For example, the implicit connection in the social graph is used to select social network page suggestions, mobile notifications, friend account suggestions, or purchase suggestions in the same manner that news feed stories are selected. The

  The feed selection module 328 presents a news feed story for a social network page when there is an implicit connection in the social graph between the user account and the social network page. The feed selection module 328 presents a news feed story for a social network page when there is an implicit connection in the social graph between the friend account of the user account and the social network page.

  In one embodiment, when selecting a news feed based on edge weights, a lower value edge weight corresponds to a higher quality content entry selected for the news feed. The quality of the content entry is specified by the social networking system 300. For example, quality is based on the number of interactions with content entries from other user accounts in social networking system 300. Sponsored content is considered higher quality. With a large value of edge weight, more content entries on the social network page are eligible to appear on the user's news feed story.

  The feed selection module 328 is for presenting one or more content entries of social network pages connected by an implicit connection in the social graph to a user account when the content entries are sponsored content. Choose as. The feed selection module 328 selects one or more content entries of the social network page for presentation to the user account when the social network page is established by the sponsor client.

The connection use module 316 includes an advertisement selection module 330. The advertisement selection module 330 is for presenting targeted advertisements to the user account based on the explicit connection in the social graph of the user account and the implicit connection in the social graph. The advertisement selection module 330 selects one or more advertisement objects of the social network page for presentation to the user account when the social network page is established by the sponsor client. The advertisement selection module 330 selects one or more advertisement objects for display on the user device signed in by the user account based on the weight of the implicit connection edge in the social graph.

  The advertisement selection module 330 presents an advertisement object related to a social network page when there is an implicit connection in the social graph between the user account and the social network page. The advertisement selection module 330 presents an advertisement object related to a social network page when there is an implicit connection in the social graph between the friend account of the user account and the social network page.

  In one embodiment, when selecting an advertising object based on edge weights, a lower value of edge weight corresponds to the selected higher quality advertising object. The quality of the advertising object is specified by the social networking system 300. For example, quality is based on the number of interactions with advertising objects from user accounts in social networking system 300. Quality is proportional to the amount of sponsor fee paid to social networking system 300. With a large value of edge weight, more advertising objects on the social network page are eligible to be presented to the user account.

  The connection utilization module 316 includes a personalization module 332. The personalization module 332 is for specifying the layout of the user portal of the user account of the social networking system 300 based on the connection in the social graph. The personalization module 332 identifies the layout by sorting the content entries for presentation or display on the user account. Each of the content entries can be selected based on a connection in the social graph, with the connection in the social graph having an edge weight specified by the weight calculation module 322. Sorting the content entries is based on the edge weight of the connection in each social graph of the content entries. The association with the greatest strength is sorted to be displayed first in the user account, such as a content entry based on an explicit connection in the social graph. Associations with lesser strength are sorted for subsequent display, such as content entries based on implicit connections in the weak social graph.

  The connection utilization module 316 includes an explanation module 334. The description module 334 is for generating a source description for the content entry selected for display. The originator description is an indicator that the user interaction has triggered the selection of the content entry. For example, if the user interaction is for a user account to share a coupon for a social network page, when a content entry is selected for a news feed, the content entry is based on that sharing of the coupon for the social network page. Is accompanied by a sender description that the content entry is selected.

The connection utilization module 316 includes a confirmation module 336. The confirmation module 336 is for generating a confirmation request for the user account based on the implicit connection in the generated social graph. The confirmation request is for converting an implicit connection in the social graph into an explicit connection in the social graph by providing the user account with an opportunity to actively subscribe to the social network page. When a content entry is selected for display by the connection usage module 316, the content entry is accompanied by a confirmation request in all cases and wherever the content entry is displayed. The sender description in the display of the content entry selected by the connection usage module 316 is accompanied by a confirmation request. For example, the confirmation request may be expressed as “Like” for the social network page when the connection generation module 314 generates an implicit connection in the social graph between the user account and the social network page. It is a user interface for requesting the user.

  The connection utilization module 316 includes a privacy control module 338. Privacy control module 338 is intended to provide user control over the use of implicit connection privacy in the social graph. For example, the user account may choose not to display any personalized content entries that are selected based on an implicit connection in the social graph. The user marks the selected content entry as spam or as content that the user is not interested in. The user configures the user account such that no implicit connection in the social graph is generated based on the user interaction of the user account, or only a limited amount is generated.

  The connection utilization module 316 includes a social signal module 340. The social signal module 340 is for presenting a connection in a social graph of a user account to a friend account of the user account. For example, the social signal module 340 presents an advertisement for a social network page to a friend account. The social signal module 340 indicates that an advertisement is being displayed because there is an explicit connection in the social graph between the user account and the social network page. The social signal module 340 indicates that the advertisement is displayed because the social network page is socially related from an implicit connection in the social graph. The social signal module 340 presents social delivery information about a social network page in advertisements and content that are presented without explicit attribution to a user account that is implicitly associated with the social network page.

  The page usage module 316 sends the selected content entry from that module to the web server 344 for presentation to the client device of the social networking system 300. The web server 344 is the web server 224 of FIG. The client device is the client device 204A of FIG.

  The technology introduced in the modules described above may be implemented by a programmable circuit programmed or configured by software and / or firmware, or by a fully dedicated “hardwired” circuit, or a combination of such forms Implemented. Such dedicated circuitry (if any) is in the form of, for example, one or more application specific integrated circuits (ASICs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), and the like.

4A-4B, an example social graph 400 illustrating the derivation of an implicit connection in a social graph through a direct interaction process based on a direct interaction that is not an explicit display of interest in social objects / pages. It is shown. FIG. 4A shows the social graph 400 before generating an implicit connection in the social graph. An implicit connection in the social graph is an implicit page connection. Social graph 400 includes a user account 402 that is connected to a social network page 404 through a trigger action 406. Trigger action 406 is defined as triggering a user interaction indicating the presence of a connection that can be an implicit connection in the social graph.

  For example, the trigger action 406 is a communication action to the social network page 404 or a reference action to the social network page 404. A communication action is a user interaction based on user communication to other social objects of the social networking system. As a specific example, the trigger action 406 is to send a message to the social network page 404, comment on the wall of the social network page 404, or answer a vote on the social network page 404. A reference action is a user interaction in which a user refers to another entity in the social networking system. As a specific example, trigger action 406 may refer to social network page 404 in a post, check in social network page 404, add a geotag that refers to social network page 404, or on a user wall. To share the social network page 404.

  FIG. 4B shows the social graph 400 after an implicit connection 408 in the social graph has been identified and added onto the social graph 400. An implicit connection 408 in the social graph connects the user account 402 and the social network page 404 to indicate the probability that the user account 402 is interested in the content of the social network page 404. An implicit connection 408 in the social graph is identified by a connection generation module, such as the connection generation module 314 of FIG. An implicit connection 408 in the social graph includes an edge weight 410. For example, the edge weight 410 is the edge weight 114 of FIG. 1 generated by the weight calculation module 322 of FIG.

  Referring now to FIGS. 5A-5C, an example social graph 500 is shown illustrating the derivation of an implicit connection in a social graph through an active reaching process based on interaction of social objects with content items. FIG. 5A shows an initial state of the social graph 500. An implicit connection in the social graph is an implicit page connection. Social graph 500 includes a user account 502. Social graph 500 also includes a social network page 504. Social network page 504 is linked to page item 506 through content association 508. Page item 506 is the content, widget, or interactive multimedia of social network page 504. Content association 508 indicates that page item 506 is unique to social network page 504. For example, page item 506 is a promotion, vote, survey question, event, coupon, content post, or any combination thereof.

  FIG. 5B shows the social graph 500 after recording the trigger action 510 and before adding the implicit connection 512 in the social graph. The trigger action 510 is to trigger a user interaction indicating the presence of a connection that can be an implicit connection in the social graph. The trigger action 510 is an enable action or a reference action. The enable action is a user interaction for enabling the function or widget of the page item 506. For example, the trigger action 510 is to claim a promotion, ask for a response to an event invitation, or answer a survey vote. As another example, the trigger action 510 is to share a content post or promotional coupon.

FIG. 5C shows the social graph 500 after an implicit connection 512 in the social graph has been identified and added onto the social graph 500. Implicit connections 512 in the social graph are identified by a connection generation module, such as connection generation module 314 of FIG. An implicit connection 512 in the social graph connects the user account 502 and the social network page 504 to indicate the probability that the user account 502 is interested in the content of the social network page 504. An implicit connection 512 in the social graph includes an edge weight 514. For example, the edge weight 514 is the edge weight 114 of FIG. 1 generated by the weight calculation module 322 of FIG. In one embodiment, edge weight 514 has a smaller value than edge weight 410 of FIG.

  Referring now to FIGS. 6A-6C, an example social graph 600 illustrating the derivation of an implicit connection in a social graph through a passive connection process based on an interaction by another account that links a user account to a social object is shown. ing. FIG. 6A shows an initial state of the social graph 600. An implicit connection in the social graph is an implicit page connection. Social graph 600 includes a user account 602. Social graph 600 also includes a social network page 604. Social network page 604 is linked to association account 606 through dialog 608. Association account 606 is an account of an entity in the social networking system with an existing explicit association with user account 602. For example, the association account 606 is a friend account of the user account 602 or a social network group of which the user account 602 is a member. The dialogue 608 is a dialogue with the social network page 604. For example, dialog 608 is a reference action or communication action as described above in FIG. For example, the dialog 608 may involve the association account 606 checking in the social network page 604, the association account 606 tagging or mentioning the social network page 604 in the photo, or the association account 606 may relate to the social network page 604. Post a comment.

  FIG. 6B shows the social graph 600 after recording the trigger action 610 and before adding an implicit connection 612 in the social graph. The trigger action 610 is a reference action. For example, trigger action 610 is that association account 606 refers to user account 602 in a comment posted to social network page 604. The trigger action 610 is that the association account 606 refers to or tags the user account 602 in a tagged photo or at check-in.

  FIG. 6C shows the social graph 600 after an implicit connection 612 in the social graph has been identified and added onto the social graph 600. An implicit connection 612 in the social graph is identified by a connection generation module, such as the connection generation module 314 of FIG. An implicit connection 612 in the social graph connects the user account 602 and the social network page 604 to indicate the probability that the user account 602 is interested in the content of the social network page 604. An implicit connection 612 in the social graph includes an edge weight 614. For example, the edge weight 614 is the edge weight 114 of FIG. 1 generated by the weight calculation module 322 of FIG. In one embodiment, edge weight 614 has a smaller value than edge weight 514 of FIG.

Referring now to FIGS. 7A-7C, an example of a social graph 700 is shown that illustrates the derivation of implicit connections in the social graph through a bridge interaction process. The bridge dialog process is based on a bridge dialog that makes clear that an implicit page connection already exists. FIG. 7A shows an initial state of the social graph 700. An implicit connection in the social graph is an implicit page connection. Social graph 700 includes a user account 702. User account 702 is linked to association account 704 by interaction A706. Alternatively or additionally, the user account 702 is linked to the association account 704 by interaction B708. For example, the association account 704 is a friend account of the user account 702 or a social network group of which the user account 702 is a member.

  Dialog A 706 is a user interaction from user account 702 to association account 704. Dialog B 708 is a user interaction from association account 704 to user account 702. Dialog A 706 and Dialog B 708 are each a reference action such as tagging or mentioning.

  Social graph 700 also includes a social network page 710. Social network page 710 is linked to page item 712 through content association 714. Page item 712 is the content, widget, or interactive multimedia of social network page 710. Content association 714 indicates that page item 712 is unique to social network page 710. For example, the page item 712 is the page item 506 in FIG. 5, and the content association 714 is the content association 508 in FIG.

  FIG. 7B shows the social graph 700 after recording the trigger action 716 and before adding an implicit connection 718 in the social graph. The trigger action 716 is a reference action or communication action to the page item 712. For example, the trigger action 716 is a post or comment on the wall of the page item 712. Trigger action 716 is a post, comment, or message that mentions and references page item 712.

  FIG. 7C shows the social graph 700 after an implicit connection 718 in the social graph has been identified and added onto the social graph 700. An implicit connection 718 in the social graph is identified by a connection generation module, such as the connection generation module 314 of FIG. An implicit connection 718 in the social graph connects the user account 702 and the social network page 710 to indicate the probability that the user account 702 is interested in the content of the social network page 710. An implicit connection 718 in the social graph includes an edge weight 720. For example, the edge weight 720 is the edge weight 114 of FIG. 1 generated by the weight calculation module 322 of FIG. In one embodiment, the edge weight 720 has a smaller value than the edge weight 614 of FIG.

  Referring now to FIGS. 8A-8B, an example social graph 800 is shown that illustrates the derivation of an implicit connection in the social graph by an account attribute process. The account attribute process can be based on shared account attributes, where at least one of the accounts already has a connection in the social graph with the intended social object. FIG. 8A shows an initial state of the social graph 800. An implicit connection in the social graph is an implicit page connection.

The social graph 800 includes a first user account 802. The first user account 802 has a first account profile 804. First account profile 804 includes profile attributes 806. Social graph 800 also includes a second user account 808. The second user account 808 includes a second account profile 810. The second account profile 810 also includes the same profile attribute 806. The second user account 808 is an association account of the first user account 802, for example, a friend account or a group of which the first user account 802 is a member. The second user account 808 is a user account in the same residence area as the first user account 802. The second user account 808 is any other user account in the social networking system. Second user account 808 is linked to social network page 812 by user interaction 814. User interaction 814 is an explicit connection in a communication action, a reference action, or a social graph. For example, the user interaction 814 is an posting of a social network page 812 to the wall, sharing the social network page 812, subscribing to the social network page 812, or an explicit “like” expression of the social network page 812. .

  FIG. 8B shows the social graph 800 after an implicit connection 816 in the social graph has been identified and added onto the social graph 800. An implicit connection 816 in the social graph is identified by a connection generation module, such as the connection generation module 314 of FIG. An implicit connection 816 in the social graph connects the first user account 802 and the social network page 812 to indicate the probability that the first user account 802 is interested in the content of the social network page 812. An implicit connection 816 in the social graph includes an edge weight 818. For example, the edge weight 818 is the edge weight 114 of FIG. 1 generated by the weight calculation module 322 of FIG. In one embodiment, edge weight 818 has a smaller value than edge weight 720 of FIG.

  Referring now to FIG. 9, a flowchart of a method 900 for operating a social networking system such as the social networking system 100 of FIG. 1 or the social networking system 202 of FIG. 2 is shown. Method 900 includes method step 902 of identifying a first user interaction on a social network system. The first user interaction is the user interaction 106 of FIG. The social network system is the social networking system 100 of FIG. 1 or the social networking system 202 of FIG. Method 900 also includes method step 904 of identifying a social network object in the social network system associated with the first user interaction by following a social graph of the social network system. Method step 904 is performed by a module of the social network system, eg, connection generation module 314 of FIG. Method 900 further includes method step 906 of identifying a user account based on the first user interaction. Method step 906 is also performed by a module of the social network system, eg, connection generation module 314 of FIG.

Once the user account and social network object are identified, the method 900 includes a method step 908 of generating an implicit connection in the social graph between the user account and the social network object. When an implicit connection in the social graph is generated, it is stored in the social graph of the social network system. Method step 908 is performed by a module of the social network system, eg, connection generation module 314 of FIG. The social network system uses the implicit connection in the added social graph through the connection use module, for example, the connection use module 316 of FIG. Method 900 includes method step 910 of selecting a content entry for display on a user device signed in by a user account or a friend account based on an implicit connection in a social graph. A friend account is defined as a socially connected account for a user account, where the social connection is defined in the social graph of the social network system.

  Referring now to FIG. 10, a machine in an exemplary form of a computer system 1000 on which a set of instructions for causing a machine to execute any one or more of the methods or modules described herein is executed. The figure which represents is shown.

  In the example of FIG. 10, the computer system 1000 includes a processor, memory, non-volatile memory, and an interface device. Various common components (eg, cache memory) have been omitted for ease of illustration. Computer system 1000 illustrates a hardware device in which any of the components shown in the examples of FIGS. 1-3 (and any other components described herein) are implemented. Is intended to be. Computer system 1000 is of any applicable known or suitable type. The components of computer system 1000 are coupled together through a bus or any other known or suitable device.

  This disclosure contemplates computer system 1000 taking any suitable physical form. By way of example, and not limitation, computer system 1000 may be an embedded computer system, a system on chip (SOC), a single board computer system (SBC) (eg, a computer on module (COM) or a system on module (SOM)). Etc.), desktop computer systems, laptop or notebook computer systems, interactive kiosks, mainframes, computer system meshes, mobile phones, personal digital assistants (PDAs), servers, or some combination thereof . Where appropriate, the computer system 1000 may include one or more computer systems 1000, be single or distributed, span multiple locations, span multiple machines, or cloud (1 One or more cloud components in one or more networks). Where appropriate, the one or more computer systems 1000 may perform one or more steps of one or more methods described or illustrated herein in substantial space or in time. Run without any restrictions. By way of example, and not limitation, one or more computer systems 1000 may perform one or more steps of one or more methods described or illustrated herein in real time, Or run in batch mode. One or more computer systems 1000 may perform one or more steps of one or more methods described or illustrated herein at different times or at different locations, where appropriate. Run.

  The processor is a conventional microprocessor such as, for example, an Intel Pentium (R) microprocessor or a Motorola Power PC microprocessor. The term “machine-readable (storage) medium” or “computer-readable (storage) medium” will be recognized by those skilled in the relevant art to include any type of device that is accessible by a processor. It will be.

  The memory is coupled to the processor, for example by a bus. The memory includes, but is not limited to, random access memory (RAM) such as dynamic RAM (DRAM) and static RAM (SRAM) by way of example. The memory can be local, remote, or distributed.

  The bus also couples the processor to non-volatile memory and a drive unit. The non-volatile memory is a magnetic floppy (registered trademark) or hard disk, magnetic optical disk, optical disk, read-only memory (ROM), such as a CD-ROM, EPROM, or EEPROM, magnetic or optical card, or another for large amounts of data. In many cases, this type of storage is used. Some of this data is often written into memory during execution of software in computer 1000 by a direct memory access process. Nonvolatile storage can be local, remote, or distributed. The nonvolatile memory is arbitrarily selected. This is because the system is created with all applicable data available in memory. A typical computer system typically includes at least a processor, memory, and a device (eg, a bus) that couples the memory to the processor.

  Software is typically stored in non-volatile memory and / or drive units. In practice, for large programs, the entire program may not be stored in memory. Nevertheless, in order for the software to run, it should be understood that, if necessary, the software is moved to a computer readable location suitable for processing, and for purposes of illustration, that location is referred to as memory in this paper. . Even when software is moved to memory for execution, the processor typically speeds up execution, typically with hardware registers to store values associated with that software Use local cache to play a role. As used herein, a software program may be any well-known or non-volatile storage (from non-volatile storage to hardware registers) where the software program is referred to as being “implemented in a computer readable medium”. It is assumed that it is stored at the preferred location. A processor is considered “configured to execute a program” if at least one value associated with the program is stored in a register readable by the processor.

  The bus also couples the processor to a network interface device. The interface includes one or more of a modem or a network interface. It will be appreciated that the modem or network interface is considered part of the computer system 1000. Interfaces include analog modems, ISDN modems, cable modems, token ring interfaces, satellite transmission interfaces (eg, “direct PC”), or other interfaces for coupling the computer system to other computer systems. The interface includes one or more input and / or output devices. I / O devices include, but are not limited to, keyboards, mice or other pointing devices, disk drives, printers, scanners, and other input and / or output devices including display devices. Display devices include, but are not limited to, cathode ray tube (CRT), liquid crystal display (LCD), or any other applicable known or suitable display device. For ease of explanation, it is assumed that a controller for any device not shown in the example of FIG. 10 is present in the interface.

In operation, computer system 1000 is controlled by operating system software that includes a file management system, such as a disk operating system. An example of operating system software with associated file management system software is the family of operating systems known as Windows® by Microsoft Corporation of Redmond, Washington, and their associated file management systems. is there. Another example of operating system software with its associated file management system software is the Linux (R) operating system and its associated file management system. File management systems are typically stored in non-volatile memory and / or drive units and include data for inputting and outputting data, and storing files on non-volatile memory and / or drive units. Causes the processor to perform various actions required by the operating system to store in memory.

  Some portions of this detailed description are presented in terms of algorithms and symbolic representations of operations on data bits in computer memory. These algorithmic descriptions and representations are the means used by engineers in the data processing arts to most effectively communicate the substance of their work to others skilled in the art. An algorithm is here and generally considered to be a consistent sequence of operations that leads to a desired result. An operation is an operation that requires physical manipulation of physical quantities. Usually, though not necessarily, these quantities are electrical or magnetic signals that can be stored, transferred, combined, compared, and otherwise manipulated. Take a form. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, words, numbers, or the like.

  It should be borne in mind, however, that all of these and similar terms are associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless stated otherwise, as will be apparent from the following discussion, throughout this description, “process,” or “calculate,” or “calculate,” or “specify,” or “display,” Or discussion using words such as "generate" manipulates data represented as physical (electronic) quantities in the computer system's registers and memory, as well as the computer system's Actions and processes of a computer system or similar electronic computing device that translates into memory or registers, or other such information storage, transmission, or other data represented as physical quantities in a display device You can see that

  The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various general purpose systems may be used with programs according to the teachings herein, or it may prove suitable to build a more specialized apparatus for performing the method of an embodiment. The required structure for a variety of these systems will appear from the description below. In addition, these techniques are not described with reference to any particular programming language, and thus various embodiments are implemented using various programming languages.

  In an alternative embodiment, this machine functions as a stand-alone device or is connected to other machines (eg, networked). In a networked deployment, this machine functions as a peer machine in the capacity of a server or client machine in a client / server network environment, or in a peer-to-peer (or distributed) network environment.

This machine is a server computer, client computer, personal computer (PC), tablet PC, laptop computer, set-top box (STB), personal digital assistant (PDA), cellular phone, iPhone (registered trademark), Blackberry (registered trademark) ), Processor, telephone, web equipment, network router, switch or bridge, or any machine that executes a set of instructions (sequence or other) that specify the action taken by that machine.

  Although a machine-readable medium or a machine-readable storage medium is shown as being a single medium in the exemplary embodiment, the terms “machine-readable medium” and “machine-readable storage medium” are one of the instructions. Or it should be understood to include a single media or multiple media (eg, centralized or distributed databases, and / or associated caches and servers) that store multiple sets. The terms “machine-readable medium” and “machine-readable storage medium” cause a machine to execute any one or more of the methods and modules of the presently disclosed techniques and innovations for execution by the machine. It should also be understood to include any media that stores, encodes, or carries a set of instructions.

  Generally, the routines executed to implement the embodiments of the present disclosure are part of an operating system or a particular application, component, program, object, module, or sequence of instructions called a “computer program” Implemented as The computer programs typically comprise one or more instructions that are set in various memory and storage devices in the computer at various times, and the instructions are one or more in the computer. When read and executed by a processing unit or processor of the present invention, causes a computer to perform operations to perform elements including various aspects of the present disclosure.

  Moreover, while embodiments have been described in the context of a fully functioning computer and computer system, the various embodiments are distributed in various forms as program products, and this disclosure is directed to the distribution Those skilled in the art will understand that the invention applies equally regardless of the particular type of machine or computer readable medium used to actually perform the process.

  Additional examples of machine readable storage media, machine readable media, or computer readable (storage) media include, among other things, volatile and non-volatile memory devices, floppies and other removable disks, hard disk drives, optical disks (eg, Recordable type media such as compact disc read only memory (CD ROM), digital versatile disc (DVD), etc., and transmission type media such as digital and analog communication links. It is not limited to.

  In some situations, the operation of the memory device may include a conversion, such as a physical conversion, such as a change in the state from binary 1 to binary 0 or vice versa. For certain types of memory devices, such physical conversion may include physically converting the article to a different state or object. For example, but not by way of limitation, for some types of memory devices, changes in state may include charge accumulation and storage, or release of stored charge. Similarly, in other memory devices, a change in state includes a physical change or transformation in the magnetic orientation, or a physical change or transformation in the molecular structure, such as from a crystalline structure to an amorphous structure or vice versa. There is a case. The above is an exhaustive list of all examples where changes in the state of binary 1 to binary 0 in the memory device and vice versa may include transformations such as physical transformations Is not intended. Rather, the above is intended as an illustrative example.

The storage medium is typically non-transitory or comprises a non-transitory device. In this context, a non-transitory storage medium can include a device that is tangible, that is, the device has a specific physical form, although it may change its physical state. . Thus, for example, “non-transitory” refers to a device that is still tangible despite this change in state.

  The above description and drawings are illustrative and are not to be construed as limiting the invention to the precise forms disclosed. Those skilled in the relevant art will appreciate that many modifications and variations are possible in light of the above disclosure. Numerous specific details are described to provide a thorough understanding of the present disclosure. In some cases, however, well-known or conventional details are not described in order to avoid obscuring the present disclosure.

  Reference to “one embodiment” or “an embodiment” herein includes a particular function, structure, or feature described in connection with that embodiment in at least one embodiment of the disclosure. Means that Where the phrase “in one embodiment” appears in various places in the specification, they do not necessarily all refer to the same embodiment; separate or alternative embodiments may In addition, other embodiments are not excluded. Moreover, various functions are described which may be illustrated by one embodiment but not by other embodiments. Similarly, various requirements are described that may be requirements for one embodiment but not other embodiments.

  As used herein, the terms “connected”, “coupled”, or any variation thereof as applied to a module of a system, are directly or indirectly between elements. Any connection or combination of any of the above, the combination of connections between those elements being physical, logical, or any combination thereof. In addition, the terms “in this specification”, “on”, “below”, and similar intent, when used in this application, refer to the present application as a whole, It does not refer to any particular part of the application. Where the context permits, words using the singular or plural number in the above “DETAILED DESCRIPTION” include the plural or singular number respectively. When referring to a list of items, the word “or (or)” refers to any of the items in the list, all of the items in the list, and of the items in the list. Including any interpretation of the word, any combination of.

  Those skilled in the art will appreciate that the present invention may be embodied in other embodiments and modes not shown hereinafter. Where there are terms that indicate a relationship, such as “first”, “second”, “top”, “bottom”, etc., the use of those terms is solely for one entity or It is done to distinguish an action from another entity or action and does not necessarily require or imply any such actual relationship or order between such entities or between actions I understand that.

  Although processes or blocks are presented in a given order, alternative embodiments employ a system that performs routines with steps in a different order or employs systems with blocks in a different order, Such processes or blocks may be deleted, moved, added, split, replaced, combined, and / or modified to provide alternative or subordinate combinations. Each of these processes or blocks is implemented in a variety of different ways. Also, although processes or blocks are shown as being executed sequentially, these processes or blocks are instead executed in parallel or at different times. Moreover, any specific numbers set forth herein are merely examples, and alternative implementations employ different values or ranges.

  The teachings of the disclosure provided herein apply to other systems, not necessarily the systems described above. The elements and acts of the various embodiments described above are combined to provide further embodiments.

  All patents and applications and other references mentioned above are hereby incorporated by reference, including all that may be listed in the accompanying application documents. Aspects of the present disclosure can be modified to employ the systems, functions, and concepts of the various references described above to provide yet another embodiment of the present disclosure where necessary.

  These and other changes are made to the disclosure in light of the above Detailed Description. Although the foregoing description describes specific embodiments of the present disclosure and describes the best mode contemplated, no matter how detailed the foregoing appears in text, the present teachings provide many Implemented in the method. The details of the system may vary considerably in its implementation details, but are still encompassed by the subject matter disclosed herein. As discussed above, a particular term used in describing a particular function or aspect of the present disclosure is any particular feature, function, or feature of the present disclosure to which the term is associated. It should not be understood to mean that it has been redefined herein to be limited to embodiments. In general, the terms used in the following claims should be read from the present disclosure, unless the foregoing Detailed Description section explicitly defines such terms. It should not be construed as limited to the particular embodiments disclosed in the specification. Accordingly, the actual scope of the disclosure encompasses not only the disclosed embodiments, but also all equivalent ways of implementing or implementing the disclosure according to the claims.

  Although certain aspects of the present disclosure are presented hereinafter in certain claim forms, the inventors contemplate the various aspects of the present disclosure in any number of claim forms. All claims intended to be handled by 35 USC 112, paragraph 6 will begin with the word "means for". Accordingly, Applicants reserve the right to pursue such additional claim forms for other aspects of the disclosure by adding additional claims after filing.

  The terms used in this specification generally have their ordinary meanings in the art, within the context of this disclosure, and in the specific context where each term is used. Certain terms used to describe the present disclosure are described above or elsewhere in the specification to provide further guidance to the practitioner regarding the description of the present disclosure. For convenience, certain terms may be highlighted, for example using capital letters, italics, and / or quotation marks. The use of highlighting does not affect the scope and meaning of a term, and the scope and meaning of a term is the same in the same context, regardless of whether the term is highlighted. It will be appreciated that the same element may be described in multiple ways.

Accordingly, alternative expressions and synonyms may be used for any one or more of the terms set forth herein, whether or not the terms are detailed or described herein. Regardless, no special meaning is given. Synonyms for specific terms are provided. The description of one or more synonyms does not exclude the use of other synonyms. Use of examples in any part of this specification, including examples of any terms set forth herein, is merely exemplary and is within the scope of any term of this disclosure or of any exemplified And is not intended to further limit its meaning. Similarly, the present disclosure is not limited to the various embodiments given herein.

  Without intending to further limit the scope of the present disclosure, examples of devices, apparatus, methods, and their associated results according to embodiments of the present disclosure are given below. It should be noted that although titles or subtitles may be used in the examples for the convenience of the reader, they are in no way intended to limit the scope of the present disclosure. Unless defined otherwise, all technical and scientific terms used herein are generally understood by those skilled in the art to which this disclosure relates. Has the same meaning. In case of conflict, this document, including definitions, controls.

  Some parts of this description describe embodiments of the present invention in terms of informational operational algorithms and symbolic representations. These algorithmic descriptions and representations are commonly used by engineers in the data processing arts to effectively communicate the work of those engineers to others skilled in the art. These operations are described functionally, computationally, or logically, but it will be understood that they are implemented by a computer program or equivalent electrical circuit, microcode, etc. Furthermore, it has been found that it is sometimes preferred to refer to these configurations of operations as modules without loss of generality. The described operations and their associated modules are embodied in software, firmware, hardware, or any combination thereof.

  Any of the steps, operations, or processes described herein are performed or implemented using one or more hardware or software modules, alone or in combination with other devices. In one embodiment, a software module comprises a computer program product comprising a computer readable medium including computer program code executed by a computer processor to perform any or all of the described steps, operations, or processes. Implemented with

  Embodiments of the invention relate to an apparatus for performing the operations herein. The apparatus comprises a general purpose computing device specially constructed for the required purpose and / or selectively enabled or reconfigured by a computer program stored in the computer. Such a computer program is stored in a non-transitory tangible computer readable storage medium coupled to a computer system bus, or any type of medium suitable for storing electronic instructions. Further, any computing system referred to herein may include a single processor or an architecture that employs a multiprocessor design to enhance computing capabilities.

  Embodiments of the present invention relate to products manufactured by the computing processes described herein. Such a product may comprise information resulting from a computing process, the information being stored on a non-transitory tangible computer readable storage medium and the computer program product or other described herein. Any embodiment of the data combination.

The language used herein is selected primarily for readability and teaching purposes and may not be selected to delineate or define the subject matter of the present invention. Accordingly, it is intended that the scope of the invention be limited not by this detailed description, but by any claims that may arise on an application based on this specification. Accordingly, the disclosure of embodiments of the invention is intended to be illustrative of the scope of the invention and is not intended to limit the scope of the invention, which is covered by the appended claims. Is shown in the range.

Claims (20)

Identifying a first user interaction on the social network system;
Identifying an social network object in the social network system associated with the first user interaction by following a social graph of the social network system;
Identifying a user account based on the first user interaction;
Generating an implicit connection in a social graph between the identified user account and the identified social network object based on the identified first user interaction;
Selecting a content entry for display on a user device based on an implicit connection in the social graph.   The method of claim 1, wherein the user account identification step includes identifying the user account that initiated the first user interaction or the user account involved in the first user interaction.   The object identification step includes identifying the social network object by identifying a link, reference, or content of the social network object that is directly or indirectly involved in the first user interaction. The method of claim 1. Generating a source description for the content entry for display on the user device signed in by the user account;
The method of claim 1, wherein the source description indicates that the first user interaction triggered the selection of the content entry.   The method of claim 1, wherein the user account identification step includes identifying the user account sharing an attribute entry that is the same as an associated account involved in the first user interaction.   The method of claim 1, further comprising receiving the first user interaction from a social plug-in to the social network system.   Generating a confirmation request for the user account based on an implied connection in the social graph, the confirmation request converting an implicit connection in the social graph into an explicit connection in the social graph; The method of claim 1, wherein Identifying a first user interaction on the social network system;
Identifying a social network page in the social network system associated with the first user interaction by following a social graph of the social network system;
Identifying a user account based on the first user interaction;
Generating an implicit connection in a social graph between the identified user account and the identified social network page based on the identified first user interaction;
Identifying a weight of an implied edge of the social graph; a weight identification step;
Selecting a content entry for display on a user device based on an implicit connection in the social graph.   9. The weight identification step includes identifying the edge weight based on a geographical proximity between a location associated with the user account and a location associated with the social network page. The method described in 1. Receiving a second user interaction involving the social network page;
9. The method of claim 8, further comprising adjusting the edge weights based on the second user interaction. Further comprising accessing an account profile of the user account;
The method of claim 8, wherein the weight identification step is based on the account profile. Further comprising accessing a page profile of the social network page including a business type;
The method of claim 8, wherein the weight identification step is based on the page profile. Further comprising generating an edge weight model based on an explicit connection in the social graph in the social graph, the edge weight model being specific to a page node type and a user account node type in the social graph;
The method of claim 8, wherein the weight identification step is based on the edge weight model.   The method of claim 8, wherein the weight identification step is based on a history of user interactions associated with the user account and the social network page.   The method of claim 14, wherein the weight identification step is based on a frequency of the first user interaction associated with the user account and the social network page.   The content entry selection step includes the step of selecting an advertising object to be displayed on the user device signed in by the user account based on the weight of the edge of an implicit connection in the social graph. The method of claim 8.   The content entry selection step includes selecting a news feed for display on the user device signed in by the user account based on the weight of the edge of an implicit connection in the social graph. The method of claim 8. A processor;
Non-temporary memory,
An action logger configured to record a first user interaction on a social network system;
A connection generation module,
Identifying a social network page in the social network system associated with the first user interaction by following a social graph of the social network system;
Identifying a user account based on the first user interaction;
The connection generation module configured to generate an implicit connection in a social graph between the user account and the social network page based on the first user interaction;
A connection utilization module configured to select a content entry for display on a user device based on an implicit connection in the social graph; and
The social networking system, wherein the action logger, the connection generation module, and the connection utilization module are implemented as instructions stored on the non-transitory memory, and the instructions are executable by the processor.   19. The social of claim 18, wherein the connection generation module is configured to identify the user account that initiated the first user interaction or the user account involved in the first user interaction. Networking system.   The connection generation module is configured to identify the social network page by identifying a link, reference, or content of the social network page that is directly or indirectly involved in the first user interaction. The social networking system according to claim 18.